Express through YouAndEye

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-destructive, non-idempotent, closed-world mutation of device state. The description adds real context beyond that: the expression is 'temporary' and 'the firmware owns animation,' which tells the agent it cannot control animation details. It omits whether a new expression replaces a currently displayed one, and does not explain the non-idempotent hint (each call produces a fresh expression).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the core action, and no filler. The second sentence is a dense conditional worth keeping, though it assumes the reader already understands what a 'sequence' is without ever defining it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter tool with 0% schema description coverage, this description is far too thin. An output schema exists so return values need not be explained, but the parameter surface and the effect of combining sequence with affect/message/priority are largely undocumented, leaving an agent to guess at correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 15 parameters, so the description carries the full burden and fails to: it explains only the sequence/message interaction. affect, gaze, ttl_ms, warmth, urgency, autonomy, priority, intensity, text_mode, confidence, behavior_mode, gaze_aversion, and cause are left entirely to enum literals and defaults, with no explanation of how they interact or which are overridden by a sequence.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: 'Show one temporary semantic expression on the local face.' That is far more informative than the bare name 'express' and its title. It does not, however, distinguish this tool from siblings like perform or neutral, so an agent cannot tell from the description alone which of the three to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

One explicit conditional rule is provided: 'When sequence is set, omit message so the device can perform its coordinated eye/OLED beat.' That is genuinely useful invocation guidance. There is no guidance on when to use express versus perform, neutral, or the face_* siblings, so routing remains inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.